改进仿射尺度不变特征变换算法的图像配准

doi:10.11772/j.issn.1001-9081.2014.05.1449

计算机应用 ›› 2014, Vol. 34 ›› Issue (5): 1449-1452.DOI: 10.11772/j.issn.1001-9081.2014.05.1449

改进仿射尺度不变特征变换算法的图像配准

范雪婷¹,²,张磊³,赵朝贺¹,²

1. 国土环境与灾害监测国家测绘地理信息局重点实验室，江苏徐州 221116；
2. 中国矿业大学环境与测绘学院，江苏徐州 221116
3. 山东中煤物探测量总公司，山东泰安 271021

收稿日期:2013-10-23 修回日期:2013-12-28 出版日期:2014-05-01 发布日期:2014-05-30
通讯作者: 范雪婷
作者简介:范雪婷(1988-)，女，吉林磐石人，硕士研究生，主要研究方向：遥感数据处理、影像匹配；张磊(1987-)，男，山东泰安人，硕士，主要研究方向：航空摄影测量、影像匹配；赵朝贺(1989-)，男，安徽宿州人，硕士研究生，主要研究方向：航空摄影测量、变化检测。
基金资助:
国家自然科学基金资助项目;江苏省测绘科研项目;国土环境与灾害监测国家测绘地理信息局重点实验室开放基金资助项目

Improved ASIFT algorithm for image registration

FAN Xueting¹,²,ZHANG Lei³,ZHAO Chaohe¹,²

1. Key Laboratory of Land Environment and Disaster Monitoring, National Administration of Surveying, Mapping and Geoinformation, Xuzhou Jiangsu 221116, China;
2. School of Environment Science and Spatial Informatics, China University of Mining and Technology, Xuzhou Jiangsu 221116, China;
3. Shandong Coal Geophysical Survey Corporation, Tai'an Shandong 271021, China

Received:2013-10-23 Revised:2013-12-28 Online:2014-05-01 Published:2014-05-30
Contact: FAN Xueting
Supported by:
National Natural Science Foundation

摘要/Abstract

摘要：

为了更好地处理匹配效率、重复纹理匹配和仿射不变性匹配等问题，对完全仿射不变特征变换（ASIFT）算法进行两方面改进。匹配框架中特征提取的改进提高了ASIFT算法的匹配效率；利用优化随机采样算法（ORSA）结合以单应矩阵为几何线性约束模型的随机抽样一致性（RANSAC）改进匹配算法，提高了匹配精度和重复纹理结构的适应能力。实验结果表明，提出的改进算法能较好地匹配高度相似纹理，计算量小，计算速度快且精度高。

Abstract:

Image registration is a well researched topic of computer vision. To deal with matching efficiency, repetitive pattern matching and affine invariant matching better, two improvements over the state-of-the-art Affine-Scale Invariant Feature Transform (ASIFT) algorithm were presented. The feature extraction of matching frame was developed to improve the matching efficiency of the ASIFT algorithm. The second increased the accuracy of matching and the adaptive capacity of repetitive patterns through the use of improved matching algorithm by combining Optimized Random Sample Consensus (ORSA) with Random Sample Consensus (RANSAC) algorithm based on geometric linear constraint model with homography matrix. The experimental results show that the proposed method is able to well match highly repetitive patterns and has smaller calculation, faster speed and higher accuracy as well.

中图分类号:

P237

范雪婷张磊赵朝贺. 改进仿射尺度不变特征变换算法的图像配准[J]. 计算机应用, 2014, 34(5): 1449-1452.

FAN Xueting ZHANG Lei ZHAO Chaohe. Improved ASIFT algorithm for image registration[J]. Journal of Computer Applications, 2014, 34(5): 1449-1452.

参考文献

［1］ZITOV B, FLUSSER J. Image registration methods: a survey ［J］. Image and Vision Computing, 2003,21(11):977-1000.
［2］LOWE D G. Distinctive image features from scale-invariant keypoints ［J］. International Journal of Computer Vision, 2004,60(2):91-110.
［3］MOREL J M, YU G. ASIFT: a new framework for fully affine invariant image comparison ［J］. SIAM Journal on Imaging Sciences, 2009,2(2):438-469.
［4］KE Y, SUKTHANKAR R. PCA-SIFT: a more distinctive representation for local image descriptors ［C］// Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2004,2:506-513.
［5］MA L, HAN X. Application of PCA method in SIFT matching algorithms ［J］. Video Engineering, 2012,36(1):129-132.(马莉,韩燮.主成分分析法(PCA)在SIFT匹配算法中的应用［J］. 电视技术,2012,36(1):129-132.）
［6］MIKOLAJCZYK K, SCHMID C. Scale & affine invariant interest point detectors ［J］. International Journal of Computer Vision, 2004,60(1):63-86.
［7］ZHANG Y, YU J, SUN J, et al. Research on corner matching method based on Harris ［J］. Computer and Modernization, 2011(11):78-81.(张勇,余建平,孙军伟,等.基于Harris的角点匹配算法研究［J］.计算机与现代化,2011(11):78-81.)
［8］ZHANG B, WANG T, LI K, et al. Improved algorithm of Harris feature point matching ［J］. Computer Systems and Applications, 2013,22(7):100-103.(张波,王天召,李科,等.一种改进的Harris特征点匹配算法［J］.计算机系统应用,2013,22(7):100-103.)
［9］MATAS J, CHUM O, URBAN M, et al. Robust wide-baseline stereo from maximally stable extremal regions ［J］. Image and Vision Computing, 2004,22(10):761-767.
［10］MO H, WANG Z. A feature detection method combined MSER and SIFT ［J］. Journal of Donghua University: Natural Science Edition, 2011,37(5):624-628. (莫会宇,王祝萍.一种结合MSER和SIFT算子的特征检测方法［J］.东华大学学报:自然科学版,2011,37(5):624-628.)
［11］MOISAN L, STIVAL B. A probabilistic criterion to detect rigid point matches between two images and estimate the fundamental matrix ［J］. International Journal of Computer Vision, 2004,57(3):201-218.
［12］ZHANG Y, WENG L, ZHANG J, et al. Homography of UAV downward-looking ground images ［J］. Application Research of Computers, 2011,28(2):749-752. (张宇，翁璐斌，张吉祥，等.无人机下视地面图像的单应约束［J］.计算机应用研究,2011,28(2):749-752.)

[1]	卢俊, 张保明, 郭海涛, 陈小卫. 利用并查集的多视匹配点提取算法[J]. 计算机应用, 2016, 36(6): 1659-1663.
[2]	夏奇郝顺义董淼任洋. 新的改进K均值粒子群算法在组合导航的应用[J]. 计算机应用, 2014, 34(5): 1397-1399.
[3]	郭海涛王鑫徐青张保明. 基于感知编组的高层建筑物立面提取方法[J]. 计算机应用, 2009, 29(09): 2389-2392.
[4]	卢俊张保明郭海涛陈小卫. 利用并查集的多视匹配点提取算法[J]. , 0, (): 0-0.
[5]	施文灶刘金清. 基于NTV和PHF的高分辨率遥感影像建筑物提取[J]. , , (): 0-0.

改进仿射尺度不变特征变换算法的图像配准

Improved ASIFT algorithm for image registration

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics